Evaluating the Ability of Generative AI to Standardize TNM Staging Data in Lung Cancer

This research chapter aims to provide a comprehensive overview of cancer cases and rates in the various states of the United States. It explores the trends and patterns of cancer incidence and mortality in the country, as well as the factors such as age, sex/gender, type of cancer whether it is lung or breast cancer and its rates and also the factors that contribute to the development and progression of the disease. The chapter reviews the latest statistics on cancer rates mainly breast and lung cancer in different population groups, including age, sex/gender, and geographical location/different states of USA. By analyzing the data, the project aims to provide insights and predictions related to the occurrence of cancer in the US. The Python code implements visualizations of cancer data for various states in the USA using Pandas and Matplotlib libraries. The dataset is read into a Pandas data frame and various types of visualizations are produced for the cancer data, including scatter plots, and bar graphs. The scatter plot represents the rate of lung and breast cancer in various states of the USA, and the bar graphs represent the total number of breast cancer and lung cancer, as well as the cancer rates in people of different age groups for each state. The visualizations allow for the comparison of cancer rates and total numbers between different states and age groups, aiding in identifying the states with higher cancer rates and potentially identifying any trends or patterns. The chapter concludes by discussing the challenges and opportunities for cancer prevention, early detection, and treatment in the United States, and the implications for public health policy and practice. Potential applications of this analysis include informing strategies for cancer prevention and treatment in different states and age groups. The project could have implications for public health and policy, as well as for advancing the understanding of cancer and its impact on society. Overall, this chapter aims to provide a comprehensive and up-to-date picture of the burden of cancer in the United States and to identify areas for further research and action.

Association Between Socioeconomic Deprivation And Cancer Incidence And Outcomes Among English CCGS

BackgroundObservational studies indicate that periodontal disease may increase the risk of colorectal, lung, and pancreatic cancers. Using a 2-sample Mendelian randomization (MR) analysis, we assessed whether a genetic predisposition index for periodontal disease was associated with colorectal, lung, or pancreatic cancer risks.MethodsOur primary instrument included single nucleotide polymorphisms with strong genome-wide association study evidence for associations with chronic, aggressive, and/or severe periodontal disease (rs729876, rs1537415, rs2738058, rs12461706, rs16870060, rs2521634, rs3826782, and rs7762544). We used summary-level genetic data for colorectal cancer (n = 58 131 cases; Genetics and Epidemiology of Colorectal Cancer Consortium, Colon Cancer Family Registry, and Colorectal Transdisciplinary Study), lung cancer (n = 18 082 cases; International Lung Cancer Consortium), and pancreatic cancer (n = 9254 cases; Pancreatic Cancer Consortia). Four MR approaches were employed for this analysis: random-effects inverse‐variance weighted (primary analyses), Mendelian Randomization-Pleiotropy RESidual Sum and Outlier, simple median, and weighted median. We conducted secondary analyses to determine if associations varied by cancer subtype (colorectal cancer location, lung cancer histology), sex (colorectal and pancreatic cancers), or smoking history (lung and pancreatic cancer). All statistical tests were 2-sided.ResultsThe genetic predisposition index for chronic or aggressive periodontitis was statistically significantly associated with a 3% increased risk of colorectal cancer (per unit increase in genetic index of periodontal disease; P = .03), 3% increased risk of colon cancer (P = .02), 4% increased risk of proximal colon cancer (P = .01), and 3% increased risk of colorectal cancer among females (P = .04); however, it was not statistically significantly associated with the risk of lung cancer or pancreatic cancer, overall or within most subgroups.ConclusionsGenetic predisposition to periodontitis may be associated with colorectal cancer risk. Further research should determine whether increased periodontitis prevention and increased cancer surveillance of patients with periodontitis is warranted.

Background Lung cancer (LC) is the top cause of cancer-related deaths globally and in Serbia, often diagnosed in advanced stage of disease with when 5-year survival is 10% to 20%. LC screening with low-dose CT (LDCT) can decrease LC mortality and overall mortality. The first pilot LC screening program in Serbia started in the Institute for Pulmonary Diseases of Vojvodina in September 2020. The main objective of this study was to analyze LC patient characteristics according to their screening status. Methods This retrospective study utilized LC hospital registry data from September 2020 to December 2023, including gender, age at diagnosis, settlement area, smoking habits, cancer histological type, TNM classification, disease stage (1-4), and data on participation in LC screening. Group differences were assessed using chi-square and Student’s t-tests, with analyses conducted in SPSS v24.0. Results During observed period from a total of 4649 LC cases 2948 (63.4%) were males, and 73 (1.6%) were included in LC screening. Average age of all LC patients was 66 years, without differences between groups (p = 0.778). Significant differences between groups by gender were find (p = 0.042). Non-screened LC patients were significantly common males compared to females (63.6% vs 36.4%), while among screened difference by gender were lower (52.1% vs 47.9%, respectively). Screened compared to non-screened LC patients have significantly lower percentage of SCLC (9.6% vs 19.1%), and higher percentage of NSCLC (90.4% vs 80.9%), (p = 0.040). According to LC stage, screened compared to non-screened patients were significantly common diagnosed in stage I of disease (45.8% vs 7.8%), and significantly less common in higher LC stages; stage IIIB (11.1% vs 22.5%), and in stage IV (22.2% vs 45.7%), (p < 0.001). Conclusions LC screening with LDCT is proven secondary preventive measure with significant influence on decreasing LC mortality by increasing number of LC patients in early stages of disease. Key messages • Lung cancer screening with low-dose CT significantly increases early-stage diagnoses, improving survival chances. • Population strategies to prevent smoking and screening programs for high-risk groups are needed to reduce lung cancer incidence and mortality rates in Serbia.

Background: Rapid economic growth, industrialization, and widespread adoption of a Western lifestyle in Vietnam have been accompanied by an emerging epidemic of noncommunicable diseases (NCDs), including cancer. We investigated current status, identified challenges and evaluated opportunities for the development of a comprehensive program in cancer epidemiology research in Vietnam. Methods: We systematically searched OvidMedline, PubMed, and the Cochrane Library for studies published in English on cancer epidemiology in Vietnam prior to November 2017. Data from Vietnam cancer registries were used for descriptive analyses. Technical reports in Vietnamese were also included in our review. Results: Cancer registry data show that by end of 2013, the total number of new cancer cases was 146,457. The most common cancers, in descending order, among men were lung, gastric, colorectal, liver and esophageal cancers while breast, lung, colorectal, gastric and thyroid cancers were the most common cancers among women. Data from six (6) cancer registries during 2004-2013 show that the incidence of several cancers has increased during the past decade, including colorectal cancer (both genders), lung cancer (men), and breast and thyroid cancers (women). Mortality data are limited due to the unavailability of death registries and/or modes of death ascertainment (i.e., causes of death). There is a scarcity of high-quality research on the risk factors (e.g., lifestyle such as smoking, alcohol consumption, physical activity, and BMI, environmental or genetic factors) for cancer in Vietnam. The majority of prior research consists of hospital-based studies (either case-control or cross-sectional designs) with small sample sizes. Since there is no population-based epidemiologic study on cancer in Vietnam, it is difficult to assess temporal trends and risk factors for cancers. Additional challenges include a lack of studies on infectious agents related to cancers and a paucity of molecular or genetic data in cancer, except for a few publications on HBV, HCV, H. Pylori, or EBV or susceptibility genes, such as BRCA1, BRCA2 for breast cancer or GSTA1, GSTP1, GSTT1 and GSTM1 for gastric cancer. Conclusions: Currently, there is no population-based epidemiologic research program for cancer in Vietnam due to the lack of a population-based cancer registry, a dearth of well-trained investigators, and the absence of proper research support infrastructure. This, along with the lack of comprehensive etiologic research in Vietnam, prevents the evaluation of the temporal trends of cancer and risk factors for cancer. The cancer registry has provided important data on cancer incidence; however, there are no data on cancer mortality. Data on molecular and genetic epidemiology of cancer are also limited. These challenges shows the need to develop a comprehensive program in cancer control in Vietnam. Citation Format: Thuan V. Tran, Chi T. Du Tran, Huong T. Tran, Mai V. Nguyen, Mo T. Tran, Quang H. Tran, Thuy Thi-Van Tuong, Martha J. Shrubsole, Qiuyin Cai, Wei Zheng, Xiao-Ou Shu, Linh C. Le, Paolo Boffetta, Hung N. Luu. Cancer epidemiology research in Vietnam: Current status, challenges and opportunities [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 1216.

The volume-outcome relationship in lung cancer surgery: The impact of the social determinants of health care delivery.

Respiratory system cancers, primarily encompassing lung cancer, tracheal cancer, bronchial cancer, and laryngeal cancer, severely jeopardize patients’ lives. Therefore, this study aimed to investigate the global burden of respiratory system cancers in 2022 using the GLOBOCAN 2022 database, to inform global prevention strategies. This study extracted data of respiratory system cancers from GLOBOCAN 2022, stratified into two subsets: laryngeal cancer (C32) and tracheal, bronchial, and lung cancers (C33, C34). It analyzed the incidence, mortality, and age-standardized rates (ASR) of both subsets across world regions, HDI levels, genders, and age groups, and projected their disease burden from 2022 to 2050. For tracheal, bronchial, and lung cancers (C33, C34), Hungary had the highest age-standardized incidence rates (ASIR) and age-standardized mortality rates (ASMR). For laryngeal cancer alone (C32), India had the highest global ASIR and ASMR. Very high HDI regions had the highest ASR for the combined cancers. Males had higher incidence and mortality than females across regions and HDI strata for both subsets. Incidence and mortality rose markedly after age 40, with faster growth in males. Projection results indicated that by 2050, the male incidence and mortality rates of tracheal, bronchial, and lung cancers would increase by 87.97% and 94.75%, respectively. For laryngeal cancer, the number of male incident cases and male deaths was expected to grow by 72.53% and 81.33%, respectively. This study, grounded in the GLOBOCAN 2022 database, elucidated the respiratory system cancers (lung cancer, tracheal cancer, bronchial cancer, and laryngeal cancer) global burden. It thereby furnished theoretical references for subsequent preventive measures.

Lung cancer is the third most common cancer in the US and is the leading cause of death. The accurate profiling of lung cancer (i.e. depiction of the magnitude of this disease among the different population subgroups at the state and local levels) is necessary to inform the development of effective cancer control programs in the areas most impacted, and subsequently, reduce the cancer burden. One of the prerequisites for accurate profiling of cancer is a high quality cancer data. Unfortunately, researchers often rely on a combination of data sources that may differ in data quality, completeness and other important attributes. The State Cancer Profiles website is perhaps the most comprehensive, and high quality resource that provides national, state and local level cancer data collected from CDC's National Program of Cancer Registries (NPCR) and NCI's Surveillance, Epidemiology and End Results (SEER) Program. Lung cancer data from State Cancer Profiles can be utilized to assess the burden and the risks, identify trends, examine sociodemographic data, expose economic, geographic and racial disparities, identify research opportunities and make important informed decisions. In this particular project, we demonstrate how State Cancer Profiles can be used effectively to profile lung cancer and identify health disparities, using the State of Indiana as an example. Method: We utilized rate/trend comparison, mortality rates, historical trends as well as screening and risk factors data to profile lung cancer mortality. A series of maps and tables were generated to communicate the geographic differences in lung cancer mortality at the local and state levels. Results: Results show how the state of Indiana compares to other states and the within state variation in cancer and risk factors. Indiana is the 7th highest state in lung cancer mortality rates. The death rate in Indiana is above the US average nonetheless, the trend is stable for females and falling for males. Orange, Wayne and White counties have the highest death rates which are above the Indiana and US averages and show rising trends. Marion County, also show death rates above the state and US averages. However, the trend is falling. In Marion County, African Americans (a predominant population in the county) have higher death rates compared to whites, 75.8 vs. 66.3. Similarly, in Allen County, African Americans have high rates compare to whites, 68.5 vs. 48.7. As far as risk factors, Indiana is the 6th highest state in the percentage of current smokers. It is noteworthy, that indoor smoking is legislated by only 30% of the state. Demographic data show that 83% of Indiana's population under the age of 65 is insured. Of the families in Indiana, 10% are below poverty. Marion County shows poverty rate at 14.2. Conclusion: The information offered by State Cancer Profiles is useful for developing a profile of cancer; for identifying the areas where cancer burden is the greatest and subgroups of populations that are most impacted. It reveals that racial disparities in lung cancer exist at both the state and county levels, despite the fact that the overall mortality rates are dropping. Furthermore, it shows the demographic characteristics and risk factors that are relevant for understanding cancer burden. In conclusion, State Cancer Profiles is an excellent tool for communicating health disparities, depicting cancer burden and informing cancer control planning. Citation Format: Antoinette Percy-Laurry, Zaria Tatalovich. Utilizing state cancer profiles for communicating lung cancer disparities. [abstract]. In: Proceedings of the Sixth AACR Conference: The Science of Cancer Health Disparities; Dec 6–9, 2013; Atlanta, GA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2014;23(11 Suppl):Abstract nr C07. doi:10.1158/1538-7755.DISP13-C07

ObjectiveRisk factors for breast, colorectal, and lung cancer are known to be more common among lesbian, gay, and bisexual (LGB) individuals, suggesting they may be more likely to develop these...

BackgroundCancers from lung and esophagus are the leading causes of cancer-related deaths in China and share many similarities in terms of histological type, risk factors and genetic variants. Recent genome-wide association studies (GWAS) in Chinese esophageal cancer patients have demonstrated six high-risk candidate single nucleotide polymorphisms (SNPs). Thus, the present study aimed to determine the risk of these SNPs predisposing to lung cancer in Chinese population.MethodsA total of 1170 lung cancer patients and 1530 normal subjects were enrolled in this study from high-incidence areas for esophageal cancer in Henan, northern China. Five milliliters of blood were collected from all subjects for genotyping. Genotyping of 20 high-risk SNP loci identified from genome-wide association studies (GWAS) on esophageal, lung and gastric cancers was performed using TaqMan allelic discrimination assays. Polymorphisms were examined for deviation from Hardy-Weinberg equilibrium (HWE) using Х2 test. Bonferroni correction was performed to correct the statistical significance of 20 SNPs with the risk of lung cancer. The Pearson’s Х2 test was used to compare the distributions of gender, TNM stage, histopathological type, smoking and family history by lung susceptibility genotypes. Kaplan-Meier and Cox regression analyses were carried out to evaluate the associations between genetic variants and overall survival.ResultsFour of the 20 SNPs identified as high-risk SNPs in Chinese esophageal cancer showed increased risk for Chinese lung cancer, which included rs3769823 (OR = 1.26; 95% CI = 1.107–1.509; P = 0.02), rs10931936 (OR = 1.283; 95% CI = 1.100–1.495; P = 0.04), rs2244438 (OR = 1.294; 95% CI = 1.098–1.525; P = 0.04) and rs13016963 (OR = 1.268; 95% CI = 1.089–1.447; P = 0.04). All these SNPs were located at 2q33 region harboringgenes of CASP8, ALS2CR12 and TRAK2. However, none of these susceptibility SNPs was observed to be significantly associated with gender, TNM stage, histopathological type, smoking, family history and overall survival.ConclusionsThe present study identified four high-risk SNPs at 2q33 locus for Chinese lung cancer and demonstrated the shared susceptibility loci at 2q33 region for Chinese lung and esophageal cancers.

Multi-class cancer diagnosis on histopathological images with deep ensemble learning model.

Background Advances in unbiased metagenomic next generation sequencing (mNGS) technologies have enabled the study of microbial and host genetic material (DNA and RNA) in one test. In this study, we aimed to develop machine learning-based differential diagnostic models (MLBDDMs) using the metagenomic and human transcriptomic data generated by an affordable bronchoalveolar lavage fluid (BLAF) mNGS assay and investigated their clinical utility for early differential diagnosis of lung cancer and pulmonary infection in patients with pulmonary diseases. Methods We recruited 775 patients with respiratory disease, including 160 pathologically diagnosed lung cancer and clinically diagnosed 615 infectious causes (131 tuberculosis, 172 fungal pneumonia and 312 bacterial pneumonia). An affordable mNGS assay on BALF samples collected from these patients on admission were performed. Using the generated mNGS data, we compared the differences in microbial diversity and host gene expression between lung cancer patients and pulmonary infection patients. The BLAF mNGS datasets of lung cancer group and each infection group were then randomly divided into a training dataset and a validation dataset at a ratio of approximately 3:1 for developing optimal MLBDDMs that can be used to distinguish lung cancer from various pulmonary infections. Results By comparing the BALF mNGS data of lung cancer (n = 160) and pulmonary infection (n = 615), we found that the infection group had higher microbial diversity than lung cancer group (P-value < 0.05). Respiratory colonizing microorganisms (e.g., Corynebacterium propinquum and Bacteroides uniformis) and pathogen (Mycobacterium tuberculosis and Cryptococcus neoformans) were found as differential microbes (adjusted p-value < 0.05, LDA score > 2). From BALF gene expression data, we detected 175 genes enriched in NOD-like receptor signaling pathway and chemokine signaling pathway differentially expressed between lung cancer and pulmonary infection groups (False Discovery Rate, FDR < 0.05). Cell composition analysis revealed that macrophage M1 was higher in lung infection group (P-value < 0.001), whereas mast cell activated and DCs activated were higher in lung cancer group (P-value < 0.001, P-value = 0.016). We integrated the metagenomic (microbial composition and human copy number variation) and transcriptomic data (host differentially expressed genes and cell composition) generated by the BALF mNGS assay with eleven machine learning classifiers to establish diagnosis models for distinguishing lung cancer from pulmonary infection (we named LC/PI model). The results showed that a Random Forest diagnostic model (the RF-LC/PI model) had optimal performance, with a sensitivity and specificity of 86.7% and 87.8%, respectively, in distinguishing lung cancer from pulmonary infection (area under the receiver operating characteristic curve [AUC] = 0.838 in the training dataset; AUC = 0.79 in a held-out validation dataset). Similar to the establishment of the LC/PI model, we further developed three diagnostic models for distinguishing lung cancer and tuberculosis (LC/TB model), lung cancer and fungal pneumonia (LC/FP model), and lung cancer and bacterial pneumonia (LC/BP model), respectively. The AUC of these three models were 0.91, 0.88, 0.91, respectively, showing a high differential diagnosis accuracy. Conclusions We have established MLBDDMs using BALF metagenomic and metatranscriptomic data and achieved superior accuracy for differentiating lung cancer and pulmonary infections, which could promote early diagnosis of pulmonary diseases and benefit more patients with one test.

Background: Lung Cancer is occasionally observed in patients with Idiopathic Pulmonary Fibrosis (IPF). We sought to describe the epidemiologic and clinical characteristics of lung cancer for patients with IPF and other interstitial lung disease (ILD) using institutional and statewide data registries. Methods: We conducted a retrospective analysis of IPF and non-IPF ILD patients from the ILD center registry, to compare with lung cancer registries at the University of Pittsburgh as well as with population data of lung cancer obtained from Pennsylvania Department of Health between 2000 and 2015. Results: Among 1108 IPF patients, 31 patients were identified with IPF and lung cancer. The age-adjusted standard incidence ratio of lung cancer was 3.34 (with IPF) and 2.3 (with non-IPF ILD) (between-group Hazard ratio = 1.4, p = 0.3). Lung cancer worsened the mortality of IPF (p < 0.001). Lung cancer with IPF had higher mortality compared to lung cancer in non-IPF ILD (Hazard ratio = 6.2, p = 0.001). Lung cancer among IPF was characterized by a predilection for lower lobes (63% vs. 26% in non-IPF lung cancer, p < 0.001) and by squamous cell histology (41% vs. 29%, p = 0.07). Increased incidence of lung cancer was observed among single lung transplant (SLT) recipients for IPF (13 out of 97, 13.4%), with increased mortality compared to SLT for IPF without lung cancer (p = 0.028) during observational period. Conclusions: Lung cancer is approximately 3.34 times more frequently diagnosed in IPF patients compared to general population, and associated with worse prognosis compared with IPF without lung cancer, with squamous cell carcinoma and lower lobe predilection. The causality between non-smoking IPF patients and lung cancer is to be determined.

Background Mitochondria are the energy factories of cells. The abnormality of mitochondrial energy metabolism pathways is closely related to the occurrence and development of lung cancer. The abnormal genes in mitochondrial energy metabolism pathways might be the novel targets and biomarkers to diagnose and treat lung cancers. Method Genes in major mitochondrial energy metabolism pathways were obtained from the KEGG database. The transcriptomic, mutation, and clinical data of lung cancers were obtained from The Cancer Genome Atlas (TCGA) database. Genes and clinical biomarkers were mined that affected lung cancer survival. Gene enrichment analysis was performed with ClusterProfiler and the gene set enrichment analysis (GSEA). STRING database and Cytoscape were used for protein-protein interaction (PPI) analysis. The diagnostic biomarker pattern of lung cancer was optimized, and its accuracy was verified with 10-fold cross-validation. The four genes screened by logistic regression model were verified by western blot in 5 pairs of lung cancer specimens collected in hospital. Results In total, 188 mitochondrial energy metabolism pathway-related genes (MMRGs) were included in this study. GSEA analysis found that MMRGs in the lung cancer group were mainly enriched in the metabolic pathway of oxidative phosphorylation and electron respiratory transport chain compared to the control group. Age did not affect the mutation frequency of MMRGs. Comparative analysis of these 188 MMRGs identified 43 differentially expressed MMRGs (24 upregulated and 19 downregulated) in the lung cancer group compared to the control group. The survival analysis of these 43 differentially expressed MMRGs found that the survival time was better in the low-expressed GAPDHS group than that in the high-expressed GAPDHS group of lung cancers. The advanced age, high expression of GAPDHS, low expressions of ACSBG1 and CYP4A11, and ACOX3 mutation were biomarkers of poor prognosis in lung cancers. PPI analysis showed that proteins such as GAPDH and GAPDHS interacted with many proteins in mitochondrial metabolic pathways. A four-MMRG-signature model (y = 0.0069∗ACADL − 0.001∗ALDH18A1 − 0.0405∗CPT1B + 0.0008∗PPARG − 1.625) was established to diagnose lung cancer with the accuracy up to 98.74%, AUC value up to 0.992, and a missed diagnosis rate of only 0.6%. Western blotting showed that ALDH18A1 and CPT1B proteins were significantly overexpressed in the lung cancer group (p < 0.05), and ACADL and PPARG proteins were slightly underexpressed in the lung cancer group (p < 0.05), which were consistent with the results of their corresponding mRNA expressions. Conclusion Mitochondrial energy metabolism pathway alterations are the important hallmarks of lung cancer. Age did not increase the risk of MMRG mutation. High expression of GAPDHS, low expression of ACSBG1, low expression of CYP4A11, mutated ACOX3, and old age predict a poor prognosis of lung cancer. Four differentially expressed MMRGs (ACADL, ALDH18A1, CPT1B, and PPARG) established a logistic regression model, which could effectively diagnose lung cancer. At the protein level, ALDH18A1 and CPT1B were significantly upregulated, and ACADL and PPARG were slightly underexpressed, in the lung cancer group compared to the control group, which were consistent with the results of their corresponding mRNA expressions.

Previous Commission on Cancer data from the National Cancer Data Base (NCDB) have examined time trends in stage of disease, treatment patterns, and survival for selected cancers. The most current (1992) data for lung cancer are described here. Four Calls for Data have yielded a total of 560,455 lung cancer cases diagnosed in 1986-1987 and 599,597 cancer cases diagnosed in 1992, from hospital cancer registries across the United States. A total of 91,115 lung cancer cases diagnosed in 1986-1987 and 92,182 diagnosed in 1992 were reported from cancer registries across the United States. Lung cancer occurs mainly in patients between the ages of 50 and 80 years. There was an increasing relative frequency of adenocarcinoma, and of lung cancer in women, and a noteworthy poor prognosis among African Americans. Lung cancer patients were reported from all types and sizes of hospitals in America, from smaller community hospitals to major teaching centers. Treatment by surgical resection occurred more frequently in the major cancer centers. The overall prognosis for lung cancer remains extremely poor. For a selective category of patients (Stage I), cancer-directed surgery offers reasonable cure rates, but these data underline the need for earlier diagnosis and improved treatment modalities in the overall management of lung cancer patients.